© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 2221
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols that typically conclude sentences or list items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.52
    ":
    
    -0.48
    Enllaces
    -0.47
     IBOutlet
    -0.46
    BufferException
    -0.45
     ब्रेकडाउन
    -0.45
    jgl
    -0.44
    󠁣
    -0.43
    shund
    -0.42
    ptonshire
    -0.42
    POSITIVE LOGITS
    \\
    1.19
    "
    1.16
    “
    1.10
    [
    1.09
    <
    1.04
    ...
    1.02
    )
    1.01
    *
    0.97
    $
    0.94
    ?
    0.93
    Activations Density 0.941%

    No Known Activations